Custom tuning

Table 1. Custom tuning features for Voci's ASR
FeatureReal-time / Post-callLocal / V‑CloudLanguagesDescription

Out-of-vocabulary (OOV)

Post-call

Both

Support rolling out to all languages; models version 7.5+ support OOV

OOV (out-of-vocabulary) is an ASR tuning feature designed to improve transcription accuracy for audio that contains brand- and industry-specific terminology. OOV enhances existing language models with new words and preferential treatment for those words.

Word substitutionsBothBothAllSubstitution is an automatic speech recognition (ASR) feature that can automatically correct errors in transcripts.
Language modelsBothBothAllThe ASR engine uses machine learning components known as models to represent knowledge about speech. This knowledge is applied during transcription. The two types of models used are acoustic models and language models. The acoustic model converts audio into a stream of sound symbols specific to a language, such as English or Spanish. The language model is responsible for converting the stream of sound symbols into text.
Custom speed tuningBothBothAllVoci provides services to custom tailor latency and throughput needs based on required SLA's and turnaround times needed.